Related Experiment Video
Updated: Jun 13, 2026
06:37
Artificial Intelligence-Based System for Detecting Attention Levels in Students
Published on: December 15, 2023
Autonomic Signature-Driven Anesthesia Depth Monitoring with Biomimetic Wearable ECG and Knowledge Graph-Augmented
1College of Smart Agriculture (College of Artificial Intelligence), Nanjing Agricultural University, Nanjing 210095, China.
Sensors (Basel, Switzerland)
|June 12, 2026
Summary
This study introduces a novel wearable electrocardiogram (ECG) system for monitoring anesthesia depth. It achieves high accuracy, offering a cost-effective alternative to traditional electroencephalogram (EEG) methods.
Area of Science:
- Biomedical Engineering
- Anesthesiology
- Artificial Intelligence
Background:
- Traditional anesthesia depth monitoring relies on electroencephalogram (EEG)-based indices like Bispectral Index (BIS), requiring specialized equipment.
- Electrocardiogram (ECG) signals are readily available, wearable-compatible, and sensitive to anesthetic agents.
Purpose of the Study:
- To develop a wearable ECG-based framework for accurate depth-of-anesthesia detection.
- To leverage autonomic nervous system characteristics and knowledge graph-enhanced graph convolutional networks (GCNs).
Main Methods:
- ECG recordings from 110 patients were analyzed, extracting 20 anesthesia-related features.
- Feature selection identified 13 discriminative features.
- A patient-level knowledge graph was constructed and utilized with a GCN for inductive inference.
Main Results:
- The proposed deep knowledge GCN achieved a test accuracy of 98.18% in distinguishing between awake and deep sleep anesthesia states.
- The system effectively utilizes ECG signals and knowledge graph learning.
Conclusions:
- Biomimetic, wearable ECG analysis combined with knowledge graph learning shows potential as a cost-effective anesthesia monitoring alternative.
- This approach offers a promising solution for patient safety during surgery.